IEEE Transactions on Neural Networks, volume 11, issue 6, pages 1373-1384
User adaptive handwriting recognition by self-growing probabilistic decision-based neural networks
Publication type: Journal Article
Publication date: 2000-01-01
Journal:
IEEE Transactions on Neural Networks
SJR: —
CiteScore: —
Impact factor: —
ISSN: 10459227, 19410093
Computer Science Applications
General Medicine
Computer Networks and Communications
Artificial Intelligence
Software
Abstract
Based on self-growing probabilistic decision-based neural networks (SPDNNs), user adaptation of the parameters of SPDNN is formulated as incremental reinforced and anti-reinforced learning procedures, which are easily integrated into the batched training procedures of the SPDNN. In this study, we developed: 1) an SPDNN based handwriting recognition system; 2) a two-stage recognition structure; and 3) a three-phase training methodology for a global coarse classifier (stage 1), a user independent hand written character recognizer (stage 2), and a user adaptation module on a personal computer. With training and testing on a 600-word commonly used Chinese character set, the recognition results indicate that the user adaptation module significantly improved the recognition accuracy. The average recognition rate increased from 44.2% to 82.4% in five adapting cycles, and the performance could finally increase up to 90.2% in ten adapting cycles.
Found
Found
Top-30
Journals
|
1
2
|
|
|
Neurocomputing
2 publications, 13.33%
|
|
|
International Journal of Fuzzy System Applications
2 publications, 13.33%
|
|
|
Lecture Notes in Computer Science
2 publications, 13.33%
|
|
|
International Journal of Human Computer Studies
1 publication, 6.67%
|
|
|
Journal of Control, Automation and Electrical Systems
1 publication, 6.67%
|
|
|
IEEE Transactions on Power Systems
1 publication, 6.67%
|
|
|
IEEE Access
1 publication, 6.67%
|
|
|
1
2
|
Publishers
|
1
2
3
|
|
|
Elsevier
3 publications, 20%
|
|
|
Springer Nature
3 publications, 20%
|
|
|
IGI Global
2 publications, 13.33%
|
|
|
Institute of Electrical and Electronics Engineers (IEEE)
2 publications, 13.33%
|
|
|
1
2
3
|
- We do not take into account publications without a DOI.
- Statistics recalculated only for publications connected to researchers, organizations and labs registered on the platform.
- Statistics recalculated weekly.
Are you a researcher?
Create a profile to get free access to personal recommendations for colleagues and new articles.
Metrics
Cite this
GOST |
RIS |
BibTex |
MLA
Cite this
GOST
Copy
Pao H. et al. User adaptive handwriting recognition by self-growing probabilistic decision-based neural networks // IEEE Transactions on Neural Networks. 2000. Vol. 11. No. 6. pp. 1373-1384.
GOST all authors (up to 50)
Copy
Pao H., Yeong Yuh Xu, Hung Yuan Chang, Hsin Chia Fu User adaptive handwriting recognition by self-growing probabilistic decision-based neural networks // IEEE Transactions on Neural Networks. 2000. Vol. 11. No. 6. pp. 1373-1384.
Cite this
RIS
Copy
TY - JOUR
DO - 10.1109/72.883451
UR - https://doi.org/10.1109/72.883451
TI - User adaptive handwriting recognition by self-growing probabilistic decision-based neural networks
T2 - IEEE Transactions on Neural Networks
AU - Pao, H.T.
AU - Yeong Yuh Xu
AU - Hung Yuan Chang
AU - Hsin Chia Fu
PY - 2000
DA - 2000/01/01
PB - Institute of Electrical and Electronics Engineers (IEEE)
SP - 1373-1384
IS - 6
VL - 11
SN - 1045-9227
SN - 1941-0093
ER -
Cite this
BibTex (up to 50 authors)
Copy
@article{2000_Pao,
author = {H.T. Pao and Yeong Yuh Xu and Hung Yuan Chang and Hsin Chia Fu},
title = {User adaptive handwriting recognition by self-growing probabilistic decision-based neural networks},
journal = {IEEE Transactions on Neural Networks},
year = {2000},
volume = {11},
publisher = {Institute of Electrical and Electronics Engineers (IEEE)},
month = {jan},
url = {https://doi.org/10.1109/72.883451},
number = {6},
pages = {1373--1384},
doi = {10.1109/72.883451}
}
Cite this
MLA
Copy
Pao, H.T., et al. “User adaptive handwriting recognition by self-growing probabilistic decision-based neural networks.” IEEE Transactions on Neural Networks, vol. 11, no. 6, Jan. 2000, pp. 1373-1384. https://doi.org/10.1109/72.883451.